# Multitask Language Understanding on MMMLU (non-EU languages, test)

Source: [Multitask Language Understanding on MMMLU (non-EU languages, test)](<https://www.sota2.com/research/sota/multitask-language-understanding-on-mmmlu-non-eu-languages-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:30:51.179Z

Evaluation of model performance on the test split of the MMMLU benchmark, specifically focusing on the non-EU languages subset, for Multitask Language Understanding, reporting Accuracy.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Multitask Language Understanding |
| Dataset (including any stated split) | MMMLU non-EU languages (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 16 of 16 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Accuracy](<https://www.sota2.com/research/sota/multitask-language-understanding-on-mmmlu-non-eu-languages-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Qwen-3-30B-A3B | 77.4 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| Qwen-3-32B | 77 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| Llama-3.3-70B | 75.5 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| Mistral-3.2-24B | 72.5 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| Qwen-3-14B | 72.4 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| Gemma-3-27B | 72.1 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| Gemma-3-12B | 66.6 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| OLMo-3.1-32B | 63 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| EuroLLM-22B (new) | 61.1 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| EuroLLM-9B (new) | 57.7 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| Apertus-70B | 57.6 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| EuroLLM-22B (old) | 56.6 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| EuroLLM-9B (old) | 51.3 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| Apertus-8B | 50.9 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| Llama-3.1-8B | 50.2 | Not recorded | 698575d8c97a0b3e3b5d5e8c |
| OLMo-3-7B | 46.4 | Not recorded | 698575d8c97a0b3e3b5d5e8c |

### Qwen-3-30B-A3B

Accuracy: 77.4. Result ID: 699647a15698665ec48b9900.

[Reporting paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Release Type":"Open-weights","Model Category":"Non-European"}. This record does not assert independent reproduction.

### Qwen-3-32B

Accuracy: 77. Result ID: 699647a15698665ec48b98ff.

[Reporting paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Release Type":"Open-weights","Model Category":"Non-European"}. This record does not assert independent reproduction.

### Llama-3.3-70B

Accuracy: 75.5. Result ID: 699647a15698665ec48b98fb.

[Reporting paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a028.md>)

[Implementation](<https://github.com/meta-llama/llama-agentic-system>)

Recorded evaluation configuration: {"Release Type":"Open-weights","Model Category":"Non-European"}. This record does not assert independent reproduction.

### Mistral-3.2-24B

Accuracy: 72.5. Result ID: 699647a15698665ec48b98f9.

[Reporting paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d61e209131cea4d909.md>)

[Implementation](<https://github.com/mistralai/mistral-src>)

Recorded evaluation configuration: {"Release Type":"Open-weights","Model Category":"European"}. This record does not assert independent reproduction.

### Qwen-3-14B

Accuracy: 72.4. Result ID: 699647a15698665ec48b98fe.

[Reporting paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Release Type":"Open-weights","Model Category":"Non-European"}. This record does not assert independent reproduction.

### Gemma-3-27B

Accuracy: 72.1. Result ID: 699647a15698665ec48b98fd.

[Reporting paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa779f1e209131cea746cd.md>)

Recorded evaluation configuration: {"Release Type":"Open-weights","Model Category":"Non-European"}. This record does not assert independent reproduction.

### Gemma-3-12B

Accuracy: 66.6. Result ID: 699647a15698665ec48b98fc.

[Reporting paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa779f1e209131cea746cd.md>)

Recorded evaluation configuration: {"Release Type":"Open-weights","Model Category":"Non-European"}. This record does not assert independent reproduction.

### OLMo-3.1-32B

Accuracy: 63. Result ID: 699647a15698665ec48b98f8.

[Reporting paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/694238e845614693628503e0.md>)

Recorded evaluation configuration: {"Release Type":"Fully-open","Model Category":"Non-European"}. This record does not assert independent reproduction.

### EuroLLM-22B (new)

Accuracy: 61.1. Result ID: 699647a15698665ec48b98f4.

[Reporting paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

Recorded evaluation configuration: {"Release Type":"Fully-open","Model Category":"European"}. This record does not assert independent reproduction.

### EuroLLM-9B (new)

Accuracy: 57.7. Result ID: 699647a15698665ec48b98f2.

[Reporting paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

Recorded evaluation configuration: {"Release Type":"Fully-open","Model Category":"European"}. This record does not assert independent reproduction.

### Apertus-70B

Accuracy: 57.6. Result ID: 699647a15698665ec48b98f6.

[Reporting paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b6c1e209131cea885c7.md>)

Recorded evaluation configuration: {"Release Type":"Fully-open","Model Category":"European"}. This record does not assert independent reproduction.

### EuroLLM-22B (old)

Accuracy: 56.6. Result ID: 699647a15698665ec48b98f3.

[Reporting paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

Recorded evaluation configuration: {"Release Type":"Fully-open","Model Category":"European"}. This record does not assert independent reproduction.

### EuroLLM-9B (old)

Accuracy: 51.3. Result ID: 699647a15698665ec48b98f1.

[Reporting paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

Recorded evaluation configuration: {"Release Type":"Fully-open","Model Category":"European"}. This record does not assert independent reproduction.

### Apertus-8B

Accuracy: 50.9. Result ID: 699647a15698665ec48b98f5.

[Reporting paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b6c1e209131cea885c7.md>)

Recorded evaluation configuration: {"Release Type":"Fully-open","Model Category":"European"}. This record does not assert independent reproduction.

### Llama-3.1-8B

Accuracy: 50.2. Result ID: 699647a15698665ec48b98fa.

[Reporting paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a028.md>)

[Implementation](<https://github.com/meta-llama/llama-agentic-system>)

Recorded evaluation configuration: {"Release Type":"Open-weights","Model Category":"Non-European"}. This record does not assert independent reproduction.

### OLMo-3-7B

Accuracy: 46.4. Result ID: 699647a15698665ec48b98f7.

[Reporting paper](<https://www.sota2.com/research/paper/698575d8c97a0b3e3b5d5e8c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/694238e845614693628503e0.md>)

Recorded evaluation configuration: {"Release Type":"Fully-open","Model Category":"Non-European"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
